{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:56:09Z","timestamp":1767034569490,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030869694"},{"type":"electronic","value":"9783030869700"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86970-0_39","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T06:03:57Z","timestamp":1631253837000},"page":"552-563","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multimodal Emotion Recognition Using Transfer Learning on Audio and Text Data"],"prefix":"10.1007","author":[{"given":"James J.","family":"Deng","sequence":"first","affiliation":[]},{"given":"Clement H. C.","family":"Leung","sequence":"additional","affiliation":[]},{"given":"Yuanxi","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,11]]},"reference":[{"issue":"4","key":"39_CR1","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42(4), 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"39_CR2","first-page":"934","volume":"16","author":"NE Cibau","year":"2013","unstructured":"Cibau, N.E., Albornoz, E.M., Rufiner, H.L.: Speech emotion recognition using a deep autoencoder. Anales de la XV Reunion de Procesamiento de la Informacion y Control 16, 934\u2013939 (2013)","journal-title":"Anales de la XV Reunion de Procesamiento de la Informacion y Control"},{"issue":"1","key":"39_CR3","first-page":"4","volume":"5","author":"JJ Deng","year":"2015","unstructured":"Deng, J.J., Leung, C.H., Milani, A., Chen, L.: Emotional states associated with music: classification, prediction of changes, and consideration in recommendation. ACM Trans. Interact. Intell. Syst. (TiiS) 5(1), 4 (2015)","journal-title":"ACM Trans. Interact. Intell. Syst. (TiiS)"},{"key":"39_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"3","key":"39_CR5","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"key":"39_CR6","unstructured":"Hamel, P., Davies, M.E., Yoshii, K., Goto, M.: Transfer learning in mir: sharing learned latent representations for music audio classification and similarity (2013)"},{"key":"39_CR7","unstructured":"Haq, S., Jackson, P.J., Edge, J.: Speaker-dependent audio-visual emotion recognition. In: AVSP, pp. 53\u201358 (2009)"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)","DOI":"10.18653\/v1\/P18-1031"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Huang, C., Gong, W., Fu, W., Feng, D.: A research of speech emotion recognition based on deep belief network and SVM. Mathematical Problems in Engineering, 2014 (2014)","DOI":"10.1155\/2014\/749604"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Z., Dong, M., Mao, Q., Zhan, Y.: Speech emotion recognition using CNN. In: Proceedings of the 22nd ACM international conference on Multimedia, pp. 801\u2013804 (2014)","DOI":"10.1145\/2647868.2654984"},{"key":"39_CR11","unstructured":"Izard, C.E., Malatesta, C.Z.: Perspectives on emotional development i: differential emotions theory of early emotional development. In: The First Draft of this Paper was Based on an Invited Address to the Eastern Psychological Association, 1 April 1983. John Wiley & Sons (1987)"},{"key":"39_CR12","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.dss.2018.09.002","volume":"115","author":"B Kratzwald","year":"2018","unstructured":"Kratzwald, B., Ili\u0107, S., Kraus, M., Feuerriegel, S., Prendinger, H.: Deep learning for affective computing: text-based emotion recognition in decision support. Decis. Support Syst. 115, 24\u201335 (2018)","journal-title":"Decis. Support Syst."},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Latif, S., Rana, R., Khalifa, S., Jurdak, R., Epps, J., Schuller, B.W.: Multi-task semi-supervised adversarial autoencoding for speech emotion recognition. IEEE Trans. Affect. Comput. abs\/1907.06078 (2019)","DOI":"10.1109\/TAFFC.2020.2983669"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Latif, S., Rana, R., Younis, S., Qadir, J., Epps, J.: Transfer learning for improving speech emotion classification accuracy. arXiv preprint arXiv:1801.06353 (2018)","DOI":"10.21437\/Interspeech.2018-1625"},{"issue":"4","key":"39_CR15","doi-asserted-by":"publisher","first-page":"1093","DOI":"10.1016\/j.asej.2014.04.011","volume":"5","author":"W Medhat","year":"2014","unstructured":"Medhat, W., Hassan, A., Korashy, H.: Sentiment analysis algorithms and applications: a survey. Ain Shams Eng. J. 5(4), 1093\u20131113 (2014)","journal-title":"Ain Shams Eng. J."},{"key":"39_CR16","unstructured":"Mehrabian, A.: Basic dimensions for a general psychological theory implications for personality, social, environmental, and developmental studies (1980)"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., Manocha, D.: M3er: multiplicative multimodal emotion recognition using facial, textual, and speech cues. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 1359\u20131367 (2020)","DOI":"10.1609\/aaai.v34i02.5492"},{"issue":"4","key":"39_CR18","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"TL Nwe","year":"2003","unstructured":"Nwe, T.L., Foo, S.W., De Silva, L.C.: Speech emotion recognition using hidden markov models. Speech Commun. 41(4), 603\u2013623 (2003)","journal-title":"Speech Commun."},{"key":"39_CR19","unstructured":"Ortony, A., Clore, G.L., Collins, A.: The Cognitive Structure of Emotions. Cambridge University Press, Cambridge (1990)"},{"issue":"10","key":"39_CR20","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"39_CR21","unstructured":"Pohle, T., Pampalk, E., Widmer, G.: Evaluation of frequently used audio features for classification of music into perceptual categories. In: Proceedings of the Fourth International Workshop on Content-Based Multimedia Indexing, vol. 162 (2005)"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Poria, S., Chaturvedi, I., Cambria, E., Hussain, A.: Convolutional MKL based multimodal emotion recognition and sentiment analysis. In: 2016 IEEE 16th international conference on data mining (ICDM), pp. 439\u2013448. IEEE (2016)","DOI":"10.1109\/ICDM.2016.0055"},{"key":"39_CR23","unstructured":"Roberts, A., Raffel, C.: Exploring transfer learning with t5: the text-to-text transfer transformer. Accessed on, pp. 23\u201307 (2020)"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Thayer, R.E.: The Biopsychology of Mood and Arousal. Oxford University Press, Oxford (1990)","DOI":"10.1093\/oso\/9780195068276.001.0001"},{"issue":"8","key":"39_CR25","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","volume":"11","author":"P Tzirakis","year":"2017","unstructured":"Tzirakis, P., Trigeorgis, G., Nicolaou, M.A., Schuller, B.W., Zafeiriou, S.: End-to-end multimodal emotion recognition using deep neural networks. IEEE J. Selected Topics Signal Process. 11(8), 1301\u20131309 (2017)","journal-title":"IEEE J. Selected Topics Signal Process."},{"key":"39_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"39_CR28","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"J Zhao","year":"2019","unstructured":"Zhao, J., Mao, X., Chen, L.: Speech emotion recognition using deep 1d & 2d cnn lstm networks. Biomed. Signal Process. Control 47, 312\u2013323 (2019)","journal-title":"Biomed. Signal Process. Control"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86970-0_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T16:33:47Z","timestamp":1699461227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86970-0_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030869694","9783030869700"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86970-0_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"11 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science and Its Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cagliari","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsa2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccsa.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Customed version of CyberChair 4","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1588","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"466","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"29% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2,5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"8","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}